SmartNews Machine Learning Engineer Interview Questions
& Process
Real candidates share what happened, how many rounds they had,
and how the experience turned out.
Based on 9 interview experiences · FREE TO READ
Candidate interview experiences
First-hand accounts from people who interviewed at SmartNews.
SmartNews
ML Engineer
Entry Average Positive experience Accept offer 4 rounds
Interview process
Technical screen Onsite Recruiter call Background check Offer
Interview formats
Coding Technical Behavioral
We had 2 rounds of coding interviews, one online and one onsite, both were LeetCode medium. There was also a machine learning interview where we discussed ad ranking or recommendation systems. Then, there was a culture fit interview, and finally, an interview with the boss.
Confirmed questions1 question
- Could you outline how you would design an ML system for ad ranking?
SmartNews
Machine Learning Engineer
Mid Average Negative experience No offer 3 rounds
Interview process
Take home Technical screen Technical screen
Interview formats
Technical Coding
The interview started with an online assessment, followed by two rounds of technical interviews. One tech round focused on ML, and the other on coding. Each round had two interviewers, one of whom was a shadow. The ML round was a bit unprofessional because they spoke Chinese, and they said the ML algorithm had a bug, even though no coding was involved. I didn't do well in the second round because I haven't practiced coding contests recently. They give hints, but it's best to start with a brute-force solution if you can't find the optimal one. None of the interviewers were from my target team.
Confirmed questions3 questions
- Can you design the logic flow for a push system given a limited budget, and how would you address any bias issues?
- What's your approach to the Subarray mod K problem?
- Solve the Subarray mod K problem. Very similar to Leetcode 974.
SmartNews
Senior Machine Learning Engineer
Senior Difficult Neutral experience No offer 2 rounds
Interview process
Technical screen Onsite
Interview formats
Coding Technical System Design
The interview process followed the track posted on the website. It involved coding questions of easy to medium complexity with explanations, deep dives into projects, and ML System Design (MLSD) and ML fundamentals. The MLSD part could be difficult, as it seemed to relate to a current problem the company is facing. I didn't answer that part well.
Confirmed questions1 question
- How would you design a system to identify premium articles, aiming to increase user subscriptions and maintain click-through rates?
SmartNews Machine Learning Engineer Interview Questions
Quoted word for word from SmartNews interview reports.
“Solve the Subarray mod K problem. Very similar to Leetcode 974.”
Read reports →“What are ML basics and how do they apply to recommendation systems?”
Read reports →“How would you go about creating a recommendation system for news?”
Read reports →“What's your approach to the Subarray mod K problem?”
Read reports →“How would you design a system to identify premium articles, aiming to increase user subscriptions and maintain click-through rates?”
Read report →“Could you outline how you would design an ML system for ad ranking?”
Read report →“Can you design a recommendation system?”
Read report →“Do you have basic ML knowledge?”
Read report →“Can you design the logic flow for a push system given a limited budget, and how would you address any bias issues?”
Read report →Formats, difficulty and experience
Across all 9 SmartNews interview reports.